gemma-4-31B-it-qat-q4_0-unquantized-abliterated

Model source

Published by huihui-ai on Hugging Face. This index organizes public repository metadata for discovery and comparison. Refer to the publisher and independent testing for actual model behavior.

Declared base model

google/gemma-4-31B-it-qat-q4_0-unquantized ↗

Hardware and context

Estimated at 18.8 GB VRAM for 31B parameters with 4-bit weights, including 15% weight overhead and 1 GB of baseline headroom. KV cache, context length, multimodal components and concurrency increase actual memory usage.The parameter count was parsed from the model name and has not been independently verified.

Context length: Not stated in public metadata. Please consult the model card.